11,848 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
Plugin Claude Code
Bundles 14 skills · 1,745 tokens together
A personal collection of reusable AI agent skills for Obsidian, planning, brainstorming, and vault management.
MCP server Claude CodeCodexCursor +2
Unified MCP server for AI-assisted development — on-demand Obsidian vault access + worker delegation. Runs locally from the hive-vault Python package. Needs 4 environment variables to run.
MCP server Claude CodeCodexCursor +2
MCP server for Cathedral — persistent memory and drift detection for AI agents. Runs locally from the cathedral-mcp Python package. Needs 3 environment variables to run.
Skill Claude CodeCodex
A filesystem-based stigmergy communication protocol. Use this to leave invisible "pheromones" (signals) on files to communicate context, risks, or status to other agents or your future self without modifying file content.
Skill Claude CodeCodex
Diagnoses bloated MEMORY.md files, splits oversized sections into domain-specific files, archives stale daily logs, and deduplicates content using a 3-tier hierarchy (MEMORY.md → domains/ → archive/). Use when MEMORY.md exceeds 10KB, context pressure is high, or the user asks to clean up, organize, or maintain agent…
Skill Claude CodeCodex
Use when searching past conversations, recalling previous solutions, understanding project history, or needing context from earlier sessions - proactive conversation history mining via ccvault MCP server.
Skill Claude CodeCodex
Audit which entries in your project's MEMORY.md Claude actually reads. Use when the user wants to find dead memory entries, broken pointers in MEMORY.md, orphan memory files, or surface entries that fall below the system-prompt truncation cutoff. Triggers on "audit MEMORY.md", "dead memory entries", "broken memory…
Skill Codex
A conversation tool that brings selected past chats into a new discussion as separate first-person advisers. It supports Reasonix and Codex session formats.
Plugin Claude Code
Bundles 7 commands · 139 tokens together
A personal knowledge system that turns raw notes into an organised, searchable wiki and can export them in an open format. It also keeps separate layers for tasks, experiences, concepts, procedures and system information.
Skill Claude CodeCodex
Record intent before the work, correct a page in place, and supersede a conclusion that has actually changed.
Plugin Claude Code
Bundles 13 skills, 8 commands, 2 agents · 1,191 tokens together
Durable state, contract and evidence layer for multi-session feature work: contract-bounded planning, autonomous phase orchestration with evidence-based acceptance, and ledger-versus-implementation review.
MCP server Claude CodeCodexCursor +2
Obsidian MCP server: semantic search, knowledge graph, and vault editing. No plugin required. Runs locally from the obsidian-brain npm package. Needs 15 environment variables to run.
baodq97/tencentdb-agent-memory
Plugin Claude Code
Bundles 8 skills, 2 commands, 1 agent, 5 hooks · 446 tokens together
Four-layer long-term memory (L0→L1→L2→L3 Persona) with hybrid FTS5+vector recall + L2 scene-navigation. CLI: tmem (status, search, projects, migrate-fragments, recall, scene, scenes, changelog, persona, sync, config, daemon, atoms, sessions, write-l1, write-scene, write-persona, mark-done, init). Run /memory-init…
Plugin Claude Code
Bundles 3 skills, 1 MCP server · 296 tokens together
Vault your Claude conversations. Captures session decisions, artifacts, and context across Code, Cowork, and Chat. Organizes memory by project, skill, and persona. Never re-explain yourself again.
Skill Claude Code
Second-brain skill for a claim-based knowledge graph in Workflowy, plus any additional services the user has configured (declared in $SECONDBRAINDIR/memory/services.md). Governs what may enter the graph (claims and actions, one claim one home, mirrors audited for drift) as well as how: capture, triage, prioritisation…
Cursor rule Cursor
Aionforge Memory cadence and vocabulary — recall first, capture as you go, track tasks as work items.
Plugin Claude Code
Bundles 3 skills, 6 commands, 3 hooks, 1 MCP server · 90 tokens together
Persistent memory with outcome-based learning for AI coding agents. Stores knowledge from coding sessions, learns which memories actually help, and gets smarter over time.
Skill Claude CodeCodex needs its repo
Full Hermespace pocket workbench for Hermes Agent (v0.18+): concept, dual decode, workbench I/O, fabric skills+MEMORY, FOA desk, Pulse, viewport app-shell, Tailscale serve, pocket boundary, autonomy grid, Desktop plugin, ops boot/doctor/smoke. Use for hermespace, pocket, workbench, FOA, pulse, viewport, access…
Skill Claude Code
Level 2 — Pantheon-native context compression with priority scoring, semantic summarization, downstream-aware compression, budget allocation, and cross-references.
Skill Claude Code
Safety, privacy, cost management, and frank advice for building always-on AI agents with episodic memory. Covers data hygiene, privacy risk surfaces, runaway cost prevention, scope creep, psychological effects of persistent AI companions, and responsible deployment patterns. This is the skill that tells you what can…
Skill Claude CodeCodex
Use Feishu Base (Bitable) as an AI agent's external brain — task management, execution logs, long-term memory, and code-driven dispatch. Activate when managing tasks, logging findings, storing memories, or running automated task scheduling.
Skill Claude CodeCodex
Personal Knowledge Management documentation system based on Zettelkasten principles. Use when documenting conversations, decisions, development work, learnings, or any knowledge that should persist. Triggers on new projects, technical decisions, completed tasks, lessons learned, meeting notes, or when the user says…
Plugin Claude Code
Bundles 3 skills, 3 hooks · 381 tokens together
Summon a project-specific LLM wiki (the Wiseman) and consult it before you code.
Plugin Claude Code
Bundles 3 commands · 4 tokens together
Never lose context in Claude Code — automatic recovery after compaction and manual session recall.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: